JP2000287955A - Image diagnostic supporting apparatus - Google Patents

Abstract

PROBLEM TO BE SOLVED: To enable easier, accurate and quick detection of abnormal shade of a breast cancer or the like. SOLUTION: In an image diagnostic supporting apparatus 1 which has an image memory means 5 for storing image data, an image display means 8 for displaying an image data stored and an abnormal shade candidate detection means 6 for detecting abnormal shade candidate by analyzing image data, the image display means 8 selects a noted region corresponding to at least one of abnormal shade candidates, sets an enlarged display window at the position of the noted region within a displayed image and displays an enlarged image in the noted region in the set enlarged display window.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image diagnosis support apparatus, and more particularly, to a doctor who performs radiological image interpretation diagnosis.
The present invention relates to an image diagnosis support device for improving the efficiency of the diagnosis.

[0002]

2. Description of the Related Art For example, when a doctor performs an image diagnosis using a radiographic image, an X-ray image is displayed on an image display device such as a CRT to perform image interpretation. In particular, in recent years, a technique for detecting abnormal shadows such as lung cancer and breast cancer by analyzing image data by using digital image processing technology by a computer has been developed, and presenting information of the detected abnormal shadow candidates to a doctor to perform diagnosis. It is becoming possible to provide support.

[0003]

When a disease such as breast cancer is diagnosed by using a mammogram image, for example, the burden on a doctor is large, and it takes a long time to interpret the image.
In particular, regarding the abnormal shadow candidate detected using the abnormal shadow detection technology, the information of the detected candidate is only the type and degree of the abnormality, the coordinates on the image, and it is not easy to know at which part the position was detected. There was a problem.

SUMMARY OF THE INVENTION The present invention has been made in view of the above circumstances, and enables easy and accurate detection of abnormal shadows such as breast cancer.
Further, it is an object of the present invention to provide an image diagnosis support device that can be performed quickly.

[0005]

Means for Solving the Problems In order to solve the above problems and achieve the object, the present invention has the following constitution.

According to a first aspect of the present invention, there is provided an image storage means for storing image data, an image display means for displaying the stored image data, and an abnormal shadow candidate detected by analyzing the image data. In the image diagnosis support apparatus having an abnormal shadow candidate detecting unit, the image display unit selects an attention area corresponding to at least one abnormal shadow candidate among the abnormal shadow candidates, and selects the attention area in a displayed image. An image diagnosis support apparatus, wherein an enlarged display window is set at a position of an area, and an enlarged image of the attention area is displayed in the set enlarged display window. ].

According to the first aspect of the present invention, an attention area corresponding to at least one of the abnormal shadow candidates is selected from the abnormal shadow candidates, and an enlarged display window is provided at the position of the attention area in the displayed image. Is set, and the enlarged image of the attention area is displayed in the enlarged display window, so that abnormal shadows can be detected easily, accurately, and quickly, and detailed qualitative diagnosis of abnormal shadows is reduced. It can be done with effort.

According to a second aspect of the present invention, there is provided an image processing apparatus comprising: an image information storing means for storing image data and finding information associated with the image data; and an image displaying means for displaying the stored image data. In the diagnosis support apparatus, the image display unit determines an abnormal shadow candidate based on the finding information corresponding to the image data, and sets a region of interest corresponding to at least one abnormal shadow candidate among the determined abnormal shadow candidates. An image-diagnosis support apparatus, wherein a magnified display window is set at a position of the selected region in a selected and displayed image, and an enlarged image of the specified region is displayed in the set magnified display window. ].

According to the second aspect of the present invention, the abnormal shadow candidate is determined based on the finding information corresponding to the image data, and the abnormal shadow candidate corresponds to at least one of the determined abnormal shadow candidates. Select an attention area, set an enlarged display window at the position of the attention area in the displayed image, and display an enlarged image of the attention area in the set enlarged display window. Can be performed easily, accurately, and quickly, and the detailed qualitative diagnosis of abnormal shadows can be performed with less effort, and the detailed qualitative diagnosis of abnormal shadows can be performed with less effort. .

According to a third aspect of the present invention, there is provided the method according to the first or second aspect, wherein an abnormal shadow candidate is given a rank, and the attention area is sequentially switched according to the given rank.
An image / diagnosis support apparatus according to claim 1. ].

According to the third aspect of the invention, by sequentially switching the attention area in accordance with the order of the abnormal shadow candidates, it is possible to perform detailed and intensive interpretation of each abnormal shadow candidate.

According to a fourth aspect of the present invention, there is provided the image diagnosis support apparatus according to the third aspect, wherein the order is determined based on the certainty factor of the abnormal shadow candidate or the type of abnormality. ].

According to the fourth aspect of the present invention, the order is determined based on the certainty factor of the abnormal shadow candidate or the type of abnormality, so that detailed and intensive interpretation of the abnormal shadow candidate can be performed.
Priority can be given in descending order of diagnostic importance.

According to a fifth aspect of the present invention, there is provided the image diagnosis support apparatus according to the third aspect, wherein the attention area is sequentially switched in accordance with a signal input from the switching signal input means. ].

According to the fifth aspect of the present invention, the switching is performed in accordance with the signal input from the switching signal input means, so that the doctor can freely change the timing according to his / her own interpretation speed or diagnostic importance, for example. Can switch.

According to a sixth aspect of the present invention, there is provided the image / diagnosis support apparatus according to the third aspect, wherein the attention area is sequentially switched at regular time intervals. ].

According to the sixth aspect of the present invention, since the attention area is sequentially switched at regular time intervals, it is possible to detect an abnormal shadow easily, accurately, and quickly without any operation error.

According to a seventh aspect of the present invention, there is provided an image diagnostic support system according to the first or second aspect, wherein different image processing is performed on an area inside and outside the enlarged display window. apparatus. ].

According to the seventh aspect of the present invention, since different image processing is performed on the area inside and outside the enlarged display window, for example, abnormal shadows on the enlarged display window can be selectively highlighted. This makes it possible to detect abnormal shadows more easily, accurately, and quickly.

According to the invention described in claim 8, the image processing is
Gradation processing, frequency processing, dynamic range compression processing,
The image / diagnosis support apparatus according to claim 7, wherein the apparatus is an interpolation process. ].

According to the present invention, by performing image processing such as gradation processing, frequency processing, dynamic range compression processing, or interpolation processing, an easy-to-read display suitable for diagnosis of an abnormal shadow candidate is provided. And abnormal shadows can be detected easily, accurately, and quickly.

According to a ninth aspect of the present invention, there is provided an image processing apparatus comprising the steps of: "determining an image processing condition based on an enlargement ratio of an image, and performing image processing based on the determined image processing condition. Image diagnosis support apparatus. ].

According to the ninth aspect of the present invention, the image processing conditions are determined based on the image enlargement ratio, and the image processing is performed based on the determined image processing conditions. In addition, it is possible to perform display in accordance with human visual characteristics, and it is possible to easily, accurately and quickly detect an abnormal shadow.

According to a tenth aspect of the present invention, there is provided the image processing apparatus according to the seventh aspect, wherein the image processing condition is determined based on the type of the abnormality, and the image processing is performed based on the determined image processing condition. Image diagnosis support device. ].

According to the tenth aspect, the image processing condition is determined based on the type of the abnormality, and the image processing is performed based on the determined image processing condition. In addition, it is possible to perform a display suitable for the image processing, and to easily, accurately, and quickly detect the abnormal shadow.

According to an eleventh aspect of the present invention, there is provided the image diagnosis support according to the first or second aspect, wherein the size of the enlarged display window is determined based on the size of the abnormal shadow candidate. apparatus. ].

According to the eleventh aspect of the present invention, the size of the enlarged display window is determined based on the size of the abnormal shadow candidate. Can be performed easily, accurately, and quickly.

According to a twelfth aspect of the present invention, there is provided the image processing apparatus according to the first or second aspect, wherein the magnification of the image is determined based on the pixel size of the image and the resolution of the image display means. Image diagnosis support device. ].

According to the twelfth aspect of the present invention, the enlargement ratio of the image is determined based on the pixel size of the image and the resolution of the image display means. And the abnormal shadow can be detected easily, accurately, and quickly.

[0030] The invention according to claim 13 is characterized in that "the enlargement ratio is
13. The image diagnosis support apparatus according to claim 12, wherein the magnification is determined to be an integral multiple of an enlargement ratio when the subject in the image is displayed at the actual size. ].

According to the thirteenth aspect, the enlargement ratio is determined to be an integral multiple of the enlargement ratio when the subject in the image is displayed at the actual size. The size of the integral multiple is intuitively easy for a diagnostician to understand, and it is easy to determine the actual size of the abnormal shadow.

According to a fourteenth aspect of the present invention, there is provided an image / diagnosis support apparatus according to the first or second aspect, wherein information on an enlargement ratio of an image is displayed together with the image. ].

According to the fourteenth aspect of the present invention, the information on the magnification of the image is displayed together with the image.
It is easy to specify the area of the abnormal shadow and to judge the size of the abnormal shadow, so that the abnormal shadow can be detected easily, accurately, and quickly.

According to a fifteenth aspect of the present invention, "the enlargement ratio is determined by using the pixel size of the image and the resolution of the image display means.
15. The image diagnosis support apparatus according to claim 14, wherein a magnification value based on an enlargement ratio when the subject in the image is displayed at the actual size is converted and displayed. ].

According to the fifteenth aspect of the present invention, the enlargement ratio is determined by using the pixel size of the image and the resolution of the image display means, based on the enlargement ratio when the subject in the image is displayed at the actual size. Since the magnification value is converted and displayed, it is easy for the diagnostician to intuitively understand, and the actual size of the abnormal shadow can be easily determined.

According to a sixteenth aspect of the present invention, it is preferable that one of the position of the enlarged display window, the size of the enlarged display window, the enlargement ratio of the image in the enlarged display window, and the image processing condition of the image in the enlarged display window be changed. 3. The image diagnosis support apparatus according to claim 1, further comprising an enlarged display control signal input unit for changing the display. ].

According to the sixteenth aspect of the present invention, the position of the enlarged display window, the size of the enlarged display window, the magnification of the image in the enlarged display window, Any of the image processing conditions of the image can be changed according to the necessity for diagnosis, and the abnormal shadow can be more easily seen, and the abnormal shadow can be detected easily, accurately, and quickly.

According to a seventeenth aspect of the present invention, there is provided the image diagnostic imaging apparatus according to the first or second aspect, wherein a mark is added near an abnormal shadow candidate position in the displayed image and displayed. Support equipment. ].

According to the seventeenth aspect of the present invention, a mark is added near the abnormal shadow candidate position in the displayed image and displayed, so that the abnormal shadow can be more easily detected by the mark, and the abnormal shadow can be detected. It can be done easily, accurately and quickly.

[0040]

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a block diagram showing the configuration of an image / diagnosis support apparatus according to an embodiment of the present invention; however, the present invention is not limited to this embodiment.

FIG. 1 is a schematic configuration diagram of an image / diagnosis support apparatus.

The image / diagnosis support apparatus 1 includes an image data input unit 2, an image output control signal input unit 3, an image processing unit 4, an image storage unit 5, an abnormal shadow candidate detection unit 6, an abnormal shadow storage unit 7, and an image output. Control means 10, image display means 8
It has a column and image printing means 9.

For input of image data from the image data input means 2, for example, in a group examination, radiographic images are usually taken using an X-ray film. A laser digitizer is used to input these radiographs into the system of this embodiment. In this method, a film is scanned with a laser beam, the amount of transmitted light is measured, and the value is converted from analog to digital to be input as digital image data.

For inputting an image, a device using an optical sensor such as a CCD can be used. Instead of reading a film, it is also possible to connect a photographing device capable of directly outputting a digital image using a stimulable phosphor as described in JP-A-55-12429. . In this case, a film is not required, and cost can be reduced.

It is also possible to manually input an X-ray image obtained from a flat panel detector (FPD) that captures an X-ray image with a plurality of two-dimensionally arranged detection elements and outputs the image as an electric signal. For example, JP-A-6-34209
As described in Japanese Patent Application Publication No. 8 (1996) -1994, there is a method in which a photoconductive layer that generates electric charges according to the intensity of irradiated X-rays and a method that accumulates the generated electric charges in a plurality of two-dimensionally arranged capacitors. Used. Further, as described in JP-A-9-90048, a photodiode or the like in which X-rays are absorbed by a phosphor layer such as an intensifying screen to generate fluorescence and the intensity of the fluorescence is provided for each pixel. A method of detecting with a photodetector is also used. Other means for detecting fluorescence include CCD and CM.
There is also a method using an OS sensor. Further, a configuration in which an X-ray scintillator that emits visible light by X-ray irradiation, a lens array, and an area sensor corresponding to each lens is also used.

When a digital X-ray image is obtained by the various configurations described above, the effective pixel size of the image may be 200 mm for a mammogram, for example, depending on the imaging site and the purpose of diagnosis.
μm or less, and more preferably 100 μm or less. In order to maximize the performance of the image diagnosis support apparatus of the present invention, for example, an effective pixel size of 5
It is preferable to store and display image data input at about 0 μm. The pixel size of the image data used in the analysis for abnormal shadow candidate detection in the abnormal shadow candidate detection means does not need to be equal to the pixel size of the input image. For example, the effective pixel size of the input image is set to 50 μm.
The image data used for abnormal shadow candidate detection may be obtained by thinning out an input image and converting it to an effective pixel size of 100 μm. The number of gradations of the image is preferably 10 bits or more, and particularly preferably 12 bits or more.

It is not necessary to limit to a simple X-ray image.
It is also possible to adopt a configuration in which image data obtained from an imaging device such as T or MRI is input.

In the image storage means 5, the input image data is subjected to data compression as required and stored. Here, as the data compression, reversible compression or irreversible compression using a known method such as JPEG, DPCM, or wavelet compression is used. Reversible compression is preferable because there is no deterioration of diagnostic information due to data compression.

In a small-scale diagnosis, since the amount of data is not so large, image data can be stored on a magnetic disk without compression. In this case, image data can be stored and read at a much higher speed than a magneto-optical disk. When reading an image, a high-speed cycle time is required, so that necessary image data is also stored in a semiconductor memory.

The images stored in the image storage unit 5 are sequentially read out, image processing is performed by the image processing unit 4, and abnormal shadow candidates are detected by the abnormal shadow detection unit 6.

The abnormal shadow detecting means 6 reads out from the image storage means 5 and analyzes the image data to detect, for example, a microcalcification cluster and a tumor shadow as shown in FIG. FIG. 22A shows an example of a microcalcification cluster. The presence of clustered microcalcifications is an important finding for finding early breast cancer, as it is likely to be early stage cancer. On the mammogram, it is seen as a small white shade with a generally conical structure. The tumor shadow shown in FIG.
On a mammogram with a certain size, it is seen as a whitish and round shadow that is close to a Gaussian distribution.

As described above, two major findings of breast cancer include a tumor shadow and a microcalcification cluster. As a method of detecting a tumor shadow, a method of detecting by comparing left and right breasts (Med. Phys., Vol. 21. no.3, p
p. 445-452), and a method of detecting using an iris filter (see IEICE (D-11), Vol. J75-D).
-11, no. 3, pp. 663-670,199
2), a method of detection using a Quoit filter (IEICE (D-11), Vol. J76-D-11, no.
3, pp. 279-287, 1993), a method of performing binarization based on a histogram of pixel values of a divided breast region and detection (JAMIT Frontier 95, pp. 84-85, 1995), a number of directional Laplacians Minimum Direction Difference Filter that Takes the Minimum Output of the Filter (IEEE (D-11), Vol. J76-D-1)
1, no. 2, pp. 241-249, 1993). Also, the method of detecting microcalcification clusters includes:
A method of localizing a region where calcification is suspected from the breast region and removing false positive candidates from the optical density difference of the shadow image and the standard deviation of the boundary density difference (IEEE Trans Biome)
d Eng BME-26 (4): 213-219,1
979), a method of detecting using an image subjected to Laplacian filter processing (IEICE (D-11), Vol. J7).
1-D-11, no. 10, pp. 1994-200
1, 1988), a detection method using an image obtained by morphological analysis to suppress the influence of a background pattern such as a mammary gland (see IEICE (D-11), Vol. J71-D-11.n).
o. 7, pp. 1170-1176, 1992).

The image to be displayed has been processed by the image processing means 5. Image processing by the image processing means 5 includes any one of gradation processing, frequency processing, and dynamic range compression processing. The gradation processing includes, in particular, image processing characterized in that a microcalcification cluster is output with stable contrast regardless of the region in the breast. In addition, the frequency processing includes, in particular, a method that creates a distance function from the skin line and performs dynamic range compression based on the distance function. Further, the image processing is characterized in that image processing under the same conditions is performed in the same direction and / or the same breast of the same patient. In the image processing, a condition may be determined for each image, or may be determined according to a predetermined condition.

When a plurality of images are simultaneously displayed on the image display means 8, it is preferable to perform image processing under the same conditions on all of the plurality of images.

A) Gradation Processing In the gradation processing, a gradation conversion curve representing the correspondence between the original image data (input) and the gradation processed image data (output) is determined based on the analysis result of the image data. Tone processing is performed using this tone conversion curve. As a method of creating a gradation conversion curve, for example, based on histogram analysis of image data, Japanese Patent Application Laid-Open No. 55-116340)
29, JP-A-63-31641, JP-A-63-2621
41 may be used. Further, Japanese Unexamined Patent Application Publication No.
As shown in -218578, a method of setting an image region corresponding to a desired portion of a subject and determining based on image data in the region may be used. As the shape of the gradation conversion curve, for example, the shape shown in JP-B-63-20535 is used. The gradation conversion curve may be created each time for each image. However, as shown in JP-A-59-83149, it is necessary to modify a reference curve selected from several kinds of reference curves created in advance. Thus, a desired gradation conversion curve may be obtained.

When the irradiation field recognition processing for detecting the irradiation field area of the radiation is performed prior to the gradation processing, various image processing conditions are set by using the image data in the recognized irradiation field area. This is preferable because image processing of an image portion required for diagnosis can be appropriately performed. As a method of this irradiation field recognition processing, for example, Japanese Unexamined Patent Publication No. 63-2595
38, JP-A-5-7579, and JP-A-7-181609 can be used.

MEDICAL IMAGING TEC
HNOLOGY Vol. 14 No. 6 November
mber 1996 Based on pages 66 to 671, a contrast correction curve is created which can correct the contrast of microcalcification images present in various regions to almost the same level. By converting the pixel values of all the pixels on the breast region image according to the correction curve, the mammary gland (fibrogranular tis) having reduced contrast is obtained.
Sue) and low-concentration area (low-d) of a mass (mass)
fat area (fat) in which the possibility that a microcalcification image is present is small.
The correction is performed so as to compress the density gradation of (area).

This contrast correction process is effective not only in improving the automatic detection performance but also in facilitating visual observation inside the mammary gland tissue, and can be applied as an image processing method. is there.

B. Frequency Processing In frequency processing, the sharpness of an image is controlled by means such as a non-sharp mask processing shown in Japanese Patent Publication Nos. 62-62373 and 62-62376 and a multi-resolution method shown in Japanese Patent Application Laid-Open No. 9-44645. be able to.

C. Dynamic range compression processing In dynamic range compression processing, for example,
The dynamic range of an arbitrary signal region can be compressed by using the method disclosed in Japanese Patent No. 503 or No. 2663189. As another example, a distance function from a skin line in a mammogram is created, and dynamic range compression is performed based on the distance function.

Since the density near the skin line is very high, there is a high possibility of blackening. This is because the mammogram imaging method takes an image across the breast. When the image is taken across the breast, the thickness of the breast is not sufficient near the skin line, so that X-rays pass through a thin human body region as compared with other regions, and the transmittance increases. In addition, the thickness of the breast decreases as the skin line approaches. For this reason, a dynamic function is compressed by creating a distance function determined by the distance from the skin line and reducing the pixel value near the skin line according to the distance function. A processing condition changing means for changing the processing conditions of the gradation processing, the frequency processing, and the dynamic range compression processing may be provided, and the changed conditions may be stored using the processing condition changing means.

In the image output signal input means 3, a mouse attached to the image display means 8 is used, for example, to change the gradation and change the gradation to a more easily diagnosable part by setting the contrast of a portion possibly having a lesion. be able to. In this case, since the contrast changes continuously with the vertical movement of the mouse, and the brightness changes with the horizontal movement of the mouse, the desired gradation can be easily changed. Further, in addition to image enlargement processing by operating a mouse, processing such as image switching, gradation change, and image enlargement is performed. The enlargement of the image is performed by hardware, and the image can be instantaneously enlarged to an arbitrary magnification by moving the mouse around the location pointed by the pointer. In addition, since interpolation processing is performed,
Even if it is enlarged, it does not become a mosaic shape and diagnosis can be easily performed.
The image processing conditions determined as described above may be stored.

For example, in a group examination, image reading is performed in 5 to 20 seconds per sheet, and images are switched one after another. However, when a button-shaped area set at the upper right on the screen is pointed by a pointer and a mouse button is pressed. Switches instantly. Normally, it just switches to the next image in order,
It is also possible to return to the previous image by clicking on an adjacent area.

The doctor interprets the displayed image data. When an abnormality is found as a result of the image interpretation, an input may be performed by designating a location where an abnormal finding has been made on the display image, and the input finding information may be stored in the finding information storage means.

As the image display means 8, known image display means such as a CRT, a liquid crystal display, and a plasma display can be used. Among them, a high-definition and high-brightness CRT or a liquid crystal display dedicated to medical images is most preferable. Further, a high definition display having a display pixel number of about 1000 × 1000 or more is preferable, and a high definition display having a display pixel number of about 2000 × 2000 or more is most preferable.

Further, for each of the displayed images, there is provided a display control number input means for controlling the display position of the image, the inversion of the image, and the rotation of the image. By performing position, image inversion, and image rotation, images can be compared and examined from various directions, and easy, quick, and accurate image diagnosis can be performed using medical images.

The image output control means 10 outputs an image to the image display means 8 or the image printing means 9 based on the image output signal of the image output signal input means 3.

The image data read from the image storage means 5 is displayed on the image display means 8. Image display means 8
Is switched and displayed as shown in FIG. 3, an all image display mode for simultaneously displaying mammogram images of all images, and all images are divided into at least two groups including a plurality of images,
A group display mode for displaying images included in the group, and display mode switching means for switching between the display modes.

In this embodiment, there is provided a display mode switching means for switching and displaying an image display mode according to a predetermined order. The CRT 20 is a four-division display (all image display) in which the left and right breasts in the same imaging direction are opposed to each other in the same direction, for example, the left and right breasts in the vertical imaging CC image and the oblique imaging MLO images are opposed to each other. ) Is performed. Next, the display is divided into two series, and in the series b, the display b1 is a two-split display (group display) in which the left and right breast MLO images are opposed to each other, the display b2 is a two-split display in which the left and right breast CC images are opposed, and the display b3 With right breast CC image and M
Two-split display with LO images facing each other, display b4: Two-split display with left breast CC images and MLO images facing each other, display b
5 Finally, the CC images of the left and right breasts are opposed to each other.
In the four-division display in which the images are opposed to each other, a mark 21 is added to the abnormal shadow candidate position of the image and displayed, and then the display returns to the first image display.

In the c-sequence, a mark 21 is added to the abnormal shadow candidate position of the image in a four-split display in which the CC images of the left and right breasts are opposed to each other in the display c1 and the MLO images are opposed to each other. Is a two-split display in which the left and right breast MLO images are opposed to each other, a display c3 is a two-split display in which the left and right breast CC images are opposed, and a display c4 is the right breast CC image and the MLO.
The image of the left breast is displayed on the split screen with the images facing each other, and the display c5 shows the CC of the left breast.
The image and the MLO image are displayed in two divisions facing each other, and then the display returns to the first image display.

The difference between the two series b and c is that the abnormal shadow detection means is displayed at an early stage or at a later stage. When the image is displayed at an early stage, the detection result of the abnormal shadow pointed out by the computer can be interpreted with particular care, which helps to reduce the burden on the doctor. If you show it at a later stage,
Since the result of the abnormal shadow detection is displayed, there is an effect of double image reading, which is useful for reducing oversight. In addition, since the two series can be freely changed, it is possible to select according to the doctor's preference or the situation of diagnosis, which is useful for improving the diagnostic performance.

Further, the images included in the group include at least two images of the same patient with different imaging directions of the left breast, or at least two images of the same patient with different imaging directions of the right breast, or a left breast and a right breast of the same patient. At least two images having different imaging directions, or at least two images having the same imaging direction of the left breast and the right breast of the same patient.

As described above, all-image display for simultaneously displaying mammogram images of all images, and group display for dividing all images into at least two groups including a plurality of images and displaying the images included in this group are performed. And 1
It is possible to compare and interpret the images of the two groups, and to make a quick, easy and accurate diagnosis.

Further, there is provided a display mode switching means for switching and displaying the image display mode in accordance with a predetermined order, and the image display mode is switched and displayed in a predetermined order. It is possible to compare images without any omission or without omission, and to easily, quickly and accurately perform image diagnosis using medical images.

Further, there is provided a diagnosis order storage means for storing the order of image diagnosis in advance, and the display mode is switched and displayed according to the order of image diagnosis. As described above, the order of the image diagnosis is stored in advance, and the display mode is switched and displayed according to the order of the image diagnosis. Therefore, it is possible to set a preferred order for each doctor and perform the diagnosis, thereby improving the diagnostic performance. It is useful for quick and accurate image diagnosis.

The image display means 8 is provided with an operation display 40 constituted by a touch panel as shown in FIG. On the touch panel, a 4-split display key 40a, a right breast display key 40b, a left breast display key 40c, an MLO image display key 40d, a CC image display key 40e, an all detection display key 40f, a mass display key 40g, and calc
A display key 40h and a cluster display key 40i are provided.

The operation of the display mode selection means 41a using the four-segment display key 40a, the right breast display key 40b, the left breast display key 40c, the MLO image display key 40d, the CC image display key 40e, and the like is necessary in advance for image diagnosis. The arrangement of the image display is determined, and each shooting direction and display direction can be freely selected. In this way, the arrangement of the image display necessary for the image diagnosis is determined in advance, and each photographing direction and display direction can be freely selected. It is possible to easily, quickly and accurately perform an image diagnosis using medical images.

The all detection display key 40f, mas
s display key 40g, calc display key 40h, plus
The mammogram detection result is displayed by the detection result display means 41b such as the ter display key 40i. All the detection results are displayed with the all detection display key 40f, and the mass detection result of the tumor shadow is calculated by operating the mass display key 40g.
By operating the display key 40h, the result of microcalcification calc detection is displayed, and by operating the cluster display key 40i, the result of microcalcification cluster detection is displayed.

After the necessary key is pressed to display the detection result, for example, by pressing the same key, the display result can be easily erased, so that only the necessary result is displayed. It can be useful for diagnosis.

Further, by switching to any one of the switching method of switching the image display mode according to a predetermined order and the switching method of switching to the display mode selected by the display mode selecting means 41a described above. For example, images can be compared without giving a physician's foresight or without omission, or images can be freely displayed and compared by a physician, etc., and easily and quickly using medical images. , Accurate image diagnosis can be performed.

Further, since patient information and examination information are stored in association with the images and a plurality of images of the same patient and the same examination are displayed, for example, by comparing the respective images, it is possible to easily and easily use the medical images. Rapid and accurate image diagnosis can be performed.

It is desirable that the patient information be relatively dark. If the color is bright, the eyes of the doctor may be tired, and the diagnostic performance may be degraded.

Further, the display position or the display image direction of the images contained in the same patient and the same examination image group can be determined according to the imaging direction and the left and right breasts.
By comparing and examining images from various directions, it is possible to easily, quickly and accurately perform image diagnosis using medical images.

As shown in FIGS. 3 and 5, it is possible to display an image of the left breast and an image of the right breast in the same patient and in the same imaging direction side by side so that the nipple faces outward. it can. In this way, by displaying the left breast image and the right breast image of the same patient and the same imaging direction side by side so that the nipple faces outward, the respective images can be compared easily and quickly. , Accurate image diagnosis can be performed.

Further, the nipple side is trimmed. Since the image size can be reduced by trimming the nipple side of the image in this manner, there is an effect of improving display speed and saving memory. Further, by displaying the patient information 55 in a part of an area where the subject on the nipple side of the image is not shown, the patient information and the subject can be displayed without overlapping so that diagnosis can be easily and accurately performed. .

Also, the left and right breasts are aligned vertically, and the left and right breasts are aligned vertically so that the image is displayed accurately in the target state and the left and right breasts are aligned. By facilitating comparison of breasts, improvement in diagnostic performance can be expected.

The vertical positioning of the left breast and the right breast is performed by automatic positioning means. In this embodiment, as shown in FIG. 5, the left and right breasts in the same imaging direction are aligned based on the skin lines 60 and 61 of the image. The skin lines 60 and 61 of the breast are substantially symmetric with respect to the chest wall 67 direction in images in the same imaging direction. The shape of the skin line can be compared, and the left and right breasts can be matched at a position where the accumulated absolute value difference of the distance from the chest wall in the same row to the skin line is minimized.
Further, the position can be similarly adjusted using the border 65 between the pectoral muscle region 63 and the breast region 64. Such positioning means facilitates comparative reading by a doctor, and more accurate diagnosis can be expected.

Further, there is provided a photographing direction discriminating means for automatically discriminating the photographing directions of the MLO image and the CC image based on the image data analysis or identification mark, and the left breast and the right breast are analyzed based on the image data by the analysis or identification mark. It has right and left breast discriminating means for automatically discriminating, and it is not necessary for the user to perform grouping as necessary, and appropriate grouping is easily performed, so that quick and accurate diagnosis can be performed. .

Further, there is provided an abnormal shadow candidate detecting means 6 for detecting an abnormal shadow candidate of the image, and the information detected by the abnormal shadow candidate detecting means 6 is stored in the abnormal shadow storing means 7.
As described above, the abnormal shadow candidate of the image is detected, and the abnormal shadow candidate is displayed. The display of the abnormal shadow candidate is shown in FIGS.
As shown in the figure, a mark is added to the abnormal shadow candidate position of the image and displayed. 6 shows an example in which a mark is attached to an abnormal shadow candidate position in mass detection of a tumor shadow, FIG. 7 shows an example in which a mark is attached to an abnormal shadow candidate position in calc detection of microcalcification, and FIG. 8 shows microlime. This is an example in which a mark is attached to an abnormal shadow candidate position in the clutter detection of image formation, and a mark is added to the abnormal shadow candidate position of such an image, so that the abnormal shadow can be easily and reliably recognized. It is possible to perform an accurate and accurate image diagnosis. The shape of the mark is not limited to those shown in FIGS. 6 to 8, and may be, for example, an arrow. Further, it is desirable to change the shape and color according to the type of the abnormal shadow.

Further, as shown in FIG. 9, a scale graduation 70 can be added to the image. By adding the scale scale 70 to the image, it is possible to easily recognize, for example, the size of an abnormal shadow or the like by the scale scale.

Further, as shown in FIG. 10, a white portion 71, a blank 72, etc. are generated in the image by the lead plate at the time of photographing.
Since it is difficult for a doctor to interpret the image if the white area is wide, the lead shielding part of the lead shielding part image is displayed in black. As described above, since the lead shielding portion of the image is displayed in black, it is not misunderstood, for example, that the lead shielding portion of the image is an abnormal shadow or the like.

The image display means 8 of the image diagnosis support apparatus 1 includes, for example, a screen without an enlarged display window shown in FIG. 11A, a screen showing an enlarged order of abnormal shadow candidates 1 in FIG. The screen is switched to a screen showing an enlarged rank 2 with the abnormal shadow candidate in FIG. On the screen without the enlarged display window in FIG. 11A, the tumor shadow of the abnormal shadow candidate is shown as rank 1 and the microcalcification cluster is shown as rank 2. FIG. 1 showing rank 1 first from the screen of FIG.
The screen of FIG. 11C is displayed in the order of the screen of FIG.

In the screens shown in FIGS. 11B and 11C, the attention area 80 corresponding to at least one of the abnormal shadow candidates is selected, and the attention area 8 in the displayed image is selected.
An enlarged display window 81 is set at a position of 0, and an enlarged image 82 of the attention area 80 is displayed in the set enlarged display window 81.
Since the enlarged image of the attention area 80 is displayed in the enlarged display window 81 in this way, abnormal shadows can be detected easily, accurately, and quickly.

In FIGS. 11B and 11C, the shape of the enlarged display window is square. However, the shape is not limited to this, and may be a circle, an ellipse, a rectangle, or another polygon. Further, for example, the shape may be distinguished depending on the type of abnormality of the abnormal shadow candidate, and the tumor cancer shadow may be circular and the microcalcification cluster may be square.

In FIGS. 11 (b) and 11 (c), the enlarged display window is surrounded by a white frame. However, the present invention is not limited to this, and may be a frame without a frame or a colored frame in the case of a color monitor. Further, for example, the color of the frame may be distinguished depending on the type of abnormality of the abnormal shadow candidate.

Further, the image display means 8 determines an abnormal shadow candidate based on the finding information corresponding to the image data, and sets an attention area 80 corresponding to at least one of the determined abnormal shadow candidates. Selecting and setting an enlarged display window 81 at the position of the noted area 80 in the displayed image,
The enlarged image 82 of the attention area 80 can be displayed in the set enlarged display window 81. As described above, the abnormal shadow candidate is determined based on the finding information corresponding to the image data, the attention area 80 corresponding to at least one abnormal shadow candidate is selected from the determined abnormal shadow candidates, and the enlarged display window 81 is selected.
Since the enlarged image 82 of the attention area 80 is displayed within the area, the abnormal shadow can be easily, accurately, and quickly detected based on the finding information.

As shown in FIG. 11, the abnormal shadow candidates are ranked, and the attention area 80 is determined in accordance with the rank.
, The abnormal shadow can be easily, accurately, and quickly detected.

By sequentially switching and displaying the regions of interest as described above, it is possible to interpret each abnormal shadow candidate in detail and intensively, and to set the region of interest for all of the plurality of abnormal shadow candidates. It is possible to prevent the overlapping and crowding of the enlarged display windows, which can occur in the first place.

In addition, the order is determined based on the certainty factor of the abnormal shadow candidate or the type of the abnormality. The certainty factor of the abnormal shadow candidate is an index indicating the degree of abnormality obtained by analyzing the image data of the candidate portion in the abnormal shadow candidate detection means 6, and includes, for example, the size, circularity, and group of microcalcification candidates. Degree of malignancy (Medic
al Imaging Tecology, vol.
14． no. 6, pp. 665-677, 1996).
Alternatively, a malignancy (JP-A-11-19077) defined based on the characteristics of a spicule associated with a tumor can be used.

In the case where the doctor's finding information is used instead of the output from the abnormal shadow candidate detecting means 6, the certainty value inputted by the doctor based on his / her own subjective evaluation can be used. In addition, the features on the image determined by the doctor
Malignant identification logic (medical electronics and biotechnology, vol.3
4, no. 4, pp. 352-357, 1996) may be used.

An embodiment of how to give a ranking will be described by taking mammography as an example.

[0102] When such an abnormal shadow candidate is detected, if the order is switched in the order of certainty, the order is: candidate 1 → candidate 2 → candidate 3 → candidate 4 →.
→ Candidate 4 → Candidate 2 → Candidate 3 →

As described above, the ranking is determined based on the certainty factor of the abnormal shadow candidate or the type of the abnormal, so that the abnormal shadow can be detected more easily, accurately, and quickly.

The switching of the attention area is performed by the switching signal input means. The switching signal input means includes a mouse button, a keyboard, a touch panel attached to a monitor, and the like, and switches the screen of the image display means 8 according to a signal input from the switching signal input means. As described above, the switching is performed according to the signal input from the switching signal input unit, so that the doctor can perform the switching at an arbitrary timing according to, for example, the certainty factor of the abnormal shadow candidate or the type of the abnormality.

For example, it is also possible to normally switch to the next region of interest by clicking the left mouse button, and to return to the immediately preceding region of interest by clicking the right mouse button as needed. Good.

Further, the attention area can be switched at regular time intervals. For example, since attention areas are sequentially switched at regular time intervals, abnormal shadows can be detected easily, accurately, and promptly without operation errors. be able to.

Further, different image processing is performed on the area inside the enlarged display window 81 and the area outside the enlarged display window 81.
One abnormal shadow can be noticed, and the abnormal shadow can be detected more easily, accurately, and quickly.

This image processing includes gradation processing, frequency processing,
There are dynamic range compression processing and interpolation processing, which have been described in detail above.

For example, different gradation processing is performed on the area inside and outside the enlarged display window 81. Specifically, a gradation processing look-up table corresponding to a different gradation conversion curve is stored in advance for an inner region and an outer region of the enlarged display window 81, and each gradation processing lookup table is displayed at the time of display. The processing data obtained by referring to the lookup table is displayed. At this time, it is preferable that the contrast of the gradation conversion curve corresponding to the area inside the enlarged display window is higher than the contrast of the gradation conversion curve corresponding to the outside area.

Further, instead of previously defining the gradation conversion curve corresponding to the area inside the enlarged display window, the image data in the enlarged display window is statistically analyzed when the enlarged display window is determined. A gradation conversion curve may be created based on the result. Specifically, the contrast of the gradation conversion curve is determined so that the substantially maximum value and the substantially minimum value of the image data in the enlarged display window are displayed at a predetermined luminance, or the integration of the image data in the enlarged display window is performed. Obtain a signal value such that the histogram value becomes a predetermined value and create a gradation conversion curve so that the signal value is displayed at a predetermined luminance, or calculate a histogram of image data in an enlarged display window. A tone conversion curve based on a known histogram equalization method is created.

Further, only the area inside the enlarged display window may be displayed in gray scale in which black and white are inverted.

As another example, different frequency processing is applied to the region inside the enlarged display window 81 and the region outside the enlarged display window 81. For example, when an unsharp mask processing method is used as the frequency processing, different mask sizes and emphasis relations are respectively recorded in the area inside the enlarged display window and the area outside the enlarged display window. The processing data calculated using the mask size and the enhancement coefficient is displayed. When the multi-resolution method is used as the frequency processing, different emphasis frequency adjustment bands and emphasis coefficients are stored in advance for the inner region and the outer region of the enlarged display window, and each emphasis frequency is displayed when the display is performed. The processing data calculated using the band and the enhancement coefficient is displayed. At that time, it is preferable that the emphasis coefficient corresponding to the area inside the enlarged display window is larger than the emphasis coefficient corresponding to the outside area. It is preferable that the frequency processing condition is determined such that the main emphasis frequency corresponding to the area inside the enlarged display window is higher than the main emphasis frequency corresponding to the outside area.

As another example, different dynamic range compression processing is performed on the area inside and outside the enlarged display window 81. For example, the dynamic range compression processing is applied only to the area outside the enlarged display window, and the dynamic registration compression processing is not applied to the area inside.

Further, with regard to the interpolation processing, when the matrix size of the image data is different from the matrix size of the display area when displaying on the image display means 8,
Interpolation processing is required. As the interpolation processing, known interpolation calculation methods such as nearest neighbor interpolation, linear interpolation, spline interpolation, cubic convolution interpolation, and bell spline interpolation can be used (IEEE Tran).
son Acoustics and Signal
Processing, vol. ASSP = 29, n
o. 6, 1981. IEEE Trans, on Me
digital Imaging. vol. M1-2, n
o3, 1983, SPIE proc, M1-11,
1988). The order of the interpolation function used for the interpolation operation is
For example, it is 0th order in nearest neighbor interpolation, 1st order in linear interpolation, and 3rd order in spline interpolation, cubic convolution interpolation, bell spline interpolation, etc. In general, the higher the higher order function is used, the more the image information is deteriorated due to the interpolation processing. Can be reduced.

As described above, in the image processing, by performing image processing such as gradation processing, frequency processing, dynamic range compression processing, interpolation processing, etc., abnormal shadows can be detected easily, accurately and quickly. it can.

The image processing conditions are determined based on the enlargement ratio. In general, even for the same image, the smaller the enlargement ratio, the higher the contrast looks visually. Therefore, when the enlargement ratio is increased, the contrast is increased. When the enlargement ratio is increased, the degree of emphasis of the frequency processing is increased. When the enlargement ratio is increased, the degree of the interpolation function of the interpolation process is increased. As described above, since the image processing conditions are determined based on the enlargement ratio, image disturbance and information deterioration due to enlargement are small, and abnormal shadows can be detected easily, accurately, and quickly.

The image processing conditions are determined based on the type of the abnormality. As described above, since the image processing condition is determined based on the type of the abnormality, it is possible to easily, accurately, and quickly detect the abnormal shadow according to the type of the abnormality.

More specifically, the contrast of the gradation conversion curve corresponding to the microcalcification is lower than the contrast of the gradation conversion curve corresponding to the tumor cancer shadow because the microcalcification has a lower object contrast than the tumor cancer shadow. Also higher. In addition, since microcalcification has a higher frequency structure than tumor shadow, the enhancement factor of the frequency processing corresponding to microcalcification may be larger than the enhancement factor corresponding to tumor shadow, or may correspond to microcalcification. The main emphasis frequency of the frequency processing to be performed is higher than the main emphasis frequency corresponding to the tumor shadow.

The size of the enlarged display window 81 is determined based on the size of the abnormal shadow candidate. For example, the size of the enlarged display window 81 is set to a size capable of displaying the entire tumor, and the microcalcification shadow included in the microcalcification cluster is set. Is set to a size that can display all of. As described above, the size of the enlarged display window 81 is determined based on the size of the abnormal shadow candidate, so that the abnormal shadow can be more easily seen.

Further, the enlargement ratio of the image is determined based on the pixel size of the image and the resolution of the image display means 8, so that the image is not disturbed by the enlargement of the image and abnormal shadows can be more easily seen.

Further, it is determined to be an integral multiple of the actual size. For example, the enlargement ratio for the actual size is the monitor size /
(Monitor resolution × pixel size of input image). By deciding to be an integral multiple of the actual size in this way, the image is the actual size in the diagnosis using the conventional film, and the actual size or the size of the integral size is easily intuitively understood by the diagnostician.

Further, when the information on the magnification of the image is displayed together with the image, it is easy to specify the portion of the abnormal shadow and to judge the size, and the abnormal shadow can be detected easily, accurately and quickly. it can.

For example, the enlargement ratio is displayed numerically in an area other than the image display area of the monitor. Alternatively, a numerical value is displayed on the periphery of the display image. The enlargement ratio may indicate both the enlargement ratio outside the enlargement display window and the inside enlargement ratio. When the pointer points outside the magnified display window, the magnification is displayed outside the magnified display window, and when the pointer is pointed inside, the magnification is displayed inside the magnified display window. You may.

As another example, the enlargement ratio inside the enlarged display window is displayed numerically adjacent to the enlarged display window 81. Alternatively, the image is displayed so as to be superimposed on the periphery of the enlarged display window 81 or a frame surrounding the enlarged display window 81. Also, besides showing the enlargement ratio numerically,
It may be indicated by an icon such as a graphic whose size is changed according to the enlargement ratio.

Further, using the pixel size of the image and the resolution of the image display means 8, the image is displayed after being converted into an enlargement ratio with respect to the actual size. As described above, the size is converted and displayed based on the actual size, so that the size can be intuitively understood by the diagnostician.

Further, the position of the enlarged display window 81, the size of the enlarged display window 81, the enlargement ratio of the image in the enlarged display window 81, and the image processing condition of the image in the enlarged display window 81 are changed. It has an enlarged display control signal input means.

This enlarged display control signal input means is constituted by the image output signal input means 3. Further, as the enlarged display control signal input means, for example, a mouse, a keyboard, a touch panel, or the like is used. For example, the position of the enlarged display window is scrolled in synchronization with the movement of the mouse. Alternatively, the enlargement ratio in the enlargement display window is continuously changed in synchronization with the movement of the mouse. Alternatively, the gradation processing condition is continuously changed in synchronization with the movement of the mouse. Specifically, by changing the average brightness in synchronization with the horizontal movement of the mouse and changing the contrast in synchronization with the vertical movement of the mouse, the gradation processing conditions can be freely and easily adjusted. Alternatively, the frequency processing condition is continuously changed in synchronization with the movement of the mouse. Specifically, the frequency processing condition can be freely set by changing the mask size of the unsharp mask processing in synchronization with the horizontal movement of the mouse and changing the enhancement coefficient of the unsharp mask processing in synchronization with the vertical movement of the mouse. And can be easily adjusted.

The change of the enlarged display state does not need to be continuous, but may be changed stepwise with a mouse button click or the like. It is also possible to adopt a configuration in which the gray level is inverted with the click of a mouse button. Also, an image output control signal input means 3 which is an enlarged display control signal input means.
After various enlarged display conditions are changed by
By transmitting the signal, the final enlarged display condition may be stored in the image information storage unit 5 in association with the image data.

As described above, the position of the enlarged display window 81, the size of the enlarged display window 81, the enlargement ratio of the image in the enlarged display window 81, and the image processing of the image in the enlarged display window 81 according to the state of the abnormal shadow and the like. By changing any of the conditions, the abnormal shadow can be more easily seen, and the abnormal shadow can be detected easily, accurately, and quickly.

Further, a mark is added to the abnormal shadow candidate position and displayed. As an example of adding this mark, for example,
A mark is added to an abnormal shadow candidate other than the abnormal shadow candidate for which the enlarged display window 81 is set. After the currently set enlarged display window, a mark is added to the abnormal shadow candidate whose enlarged display window 81 is to be set. Also, a mark having a different shape is added for each type of abnormality or for each certainty degree of abnormality.
Marks of different colors are added for each type of abnormality or for each degree of certainty of abnormality. Marks of different sizes are added for each type of abnormality or for each degree of certainty of abnormality. Marks of different colors are added to the abnormal shadow candidate to which the enlarged display window has already been applied and the abnormal shadow candidate to which the enlarged display window has not been applied. Since the mark is added to the abnormal shadow candidate position and displayed, the abnormal shadow can be more easily found by the mark, and the abnormal shadow can be detected easily, accurately, and quickly.

In FIG. 11, the mark is displayed as an arrow mark in the vicinity where it does not overlap with the abnormal shadow candidate.
The present invention is not limited to this, and may be displayed as a closed curve mark surrounding the abnormal shadow candidate as shown in FIGS. 6, 7, and 8. Also,
For example, the display may be switched between display and non-display by selecting using a button mouse set on the screen.

The image displayed on the image display means 8 can be printed on a film or paper by the image printing means 9 as it is or edited.

[0133]

As described above, according to the first aspect of the present invention, an attention area corresponding to at least one of the abnormal shadow candidates is selected from among the abnormal shadow candidates, and the position of the attention area in the displayed image is selected. Since an enlarged display window is set and an enlarged image of the attention area is displayed in the enlarged display window, abnormal shadows can be detected easily, accurately, and quickly, and the detailed quality of the abnormal shadows can be improved. Target diagnosis can be performed with less effort.

According to the second aspect of the present invention, the abnormal shadow candidate is determined based on the finding information corresponding to the image data, and the attention area corresponding to at least one of the determined abnormal shadow candidates is determined. Select, set the enlarged display window at the position of the attention area in the displayed image, and display the enlarged image of the attention area in the set enlargement display window, making it easy to detect abnormal shadows based on the finding information In addition to being able to perform accurate and quick, detailed qualitative diagnosis of abnormal shadows can be performed with little effort, and detailed qualitative diagnosis of abnormal shadows can be performed with little effort.

According to the third aspect of the present invention, by sequentially switching the attention area according to the order of the abnormal shadow candidates, it is possible to read each abnormal shadow candidate in detail and intensively.

According to the fourth aspect of the present invention, the order is determined based on the certainty factor of the abnormal shadow candidate or the type of abnormality. Therefore, detailed and intensive interpretation of the abnormal shadow candidate is performed with high diagnostic importance. It can be done in priority order.

According to the fifth aspect of the present invention, since the switching is performed in accordance with the signal input from the switching signal input means, the doctor can switch at an arbitrary timing in accordance with, for example, his / her own reading speed or diagnostic importance. it can.

According to the sixth aspect of the present invention, since the attention area is sequentially switched at regular time intervals, abnormal shadows can be detected easily, accurately, and promptly without operation errors.

According to the seventh aspect of the present invention, since different image processing is performed on the area inside and outside the enlarged display window, for example, abnormal shadows on the enlarged display window can be selectively made noticeable. Detection of abnormal shadows can be made easier, more accurate, and faster.

According to the eighth aspect of the present invention, by performing image processing such as gradation processing, frequency processing, dynamic range compression processing, or interpolation processing, an easy-to-read display suitable for diagnosis of an abnormal shadow candidate, for example, is possible. Yes, abnormal shadows can be detected easily, accurately, and quickly.

According to the ninth aspect of the present invention, the image processing conditions are determined based on the enlargement ratio of the image, and the image processing is performed based on the determined image processing conditions. The display can be performed according to the visual characteristics, and the abnormal shadow can be detected easily, accurately, and quickly.

According to the tenth aspect of the present invention, image processing conditions are determined based on the type of abnormality, and image processing is performed based on the determined image processing condition. Display can be performed, and abnormal shadows can be detected easily, accurately, and quickly.

According to the eleventh aspect of the present invention, the size of the enlarged display window is determined based on the size of the abnormal shadow candidate, so that the entire abnormal shadow candidate is always displayed in an easily viewable manner, and the abnormal shadow can be easily detected. It can be performed accurately and quickly.

According to the twelfth aspect of the present invention, since the enlargement ratio of the image is determined based on the pixel size of the image and the resolution of the image display means, the image is not disturbed by the enlargement of the image, and the abnormal shadow is more visible. The detection of abnormal shadows can be performed easily, accurately, and quickly.

According to the thirteenth aspect, the enlargement ratio is:
Since the magnification in the case where the subject in the image is displayed at the actual size is determined to be an integral multiple, the size of the actual size or the integral multiple thereof is intuitively understandable for a diagnostician, and the actual size of the abnormal shadow can be easily understood. Is easy to determine.

According to the fourteenth aspect of the present invention, since information relating to the enlargement ratio of the image is displayed together with the image, it is easy to specify the area of the abnormal shadow and to judge the size, and the abnormal shadow can be easily and accurately detected. And can be performed quickly.

According to the fifteenth aspect of the present invention, the enlargement ratio is determined by using the pixel size of the image and the resolution of the image display means.
When the subject in the image is displayed in full size, it is converted to a magnification value based on the magnification and displayed, so it is easy for the physician to understand intuitively and the actual size of the abnormal shadow is easy to judge. It is.

According to the sixteenth aspect of the present invention, the position of the enlarged display window, the size of the enlarged display window, the magnification of the image in the enlarged display window, and the size of the image in the enlarged display window are determined according to the state of the abnormal shadow. Any of the image processing conditions can be changed according to the necessity for diagnosis, and the abnormal shadow can be more easily seen, and the abnormal shadow can be detected easily, accurately, and quickly.

According to the seventeenth aspect of the present invention, since a mark is added near the abnormal shadow candidate position in the indicated image and displayed, the abnormal shadow can be more easily detected by the mark, and the abnormal shadow can be easily detected. Accurate and quick.

[Brief description of the drawings]

FIG. 1 is a schematic configuration diagram of an image diagnosis support apparatus.

FIG. 2 is a diagram showing detection of a microcalcification cluster and a tumor shadow.

FIG. 3 is a diagram showing an image switching display.

FIG. 4 is a diagram illustrating a display operation.

FIG. 5 is a diagram in which an image of a left breast and an image of a right breast in the same patient and in the same imaging direction are arranged and displayed side by side so that the nipple faces outward.

FIG. 6 is a diagram showing an example in which a mark is attached to an abnormal shadow candidate position in mass detection of a tumor shadow.

FIG. 7 is a diagram showing an example in which marks are attached to abnormal shadow candidate positions in calc detection of microcalcification.

FIG. 8 is a diagram illustrating an example in which a mark is attached to an abnormal shadow candidate position in cluster detection of microcalcification.

FIG. 9 is a diagram in which a scale is added to an image.

FIG. 10 is a diagram showing a state in which a white portion, a blank portion, or the like occurs due to a lead plate at the time of capturing an image.

FIG. 11 is a diagram illustrating switching to a screen without an enlarged display window, a screen showing an enlarged order of abnormal shadow candidates, and a screen showing an enlarged order of abnormal shadow candidates.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Image diagnosis support apparatus 2 Image data input means 3 Image output signal input means 4 Image processing means 5 Image storage means 6 Abnormal shadow candidate detection means 7 Abnormal shadow storage means 8 Image display means 9 Image printing means 10 Image output control means

 ──────────────────────────────────────────────────続 き Continued on the front page F term (reference) 4C093 AA26 AA27 AA30 FF08 FF13 FF16 FF17 5B057 AA08 CC03 CD05 CE01 CE11 CH11 CH18 5C082 AA04 AA27 BA20 BB44 CA01 CA11 CA33 CA54 CB01 CB06 DA26 DA51 DA87 MM02 MM02MM

Claims (17)

[Claims] An image storage means for storing image data, an image display means for displaying the stored image data, and an abnormal shadow candidate detection means for detecting an abnormal shadow candidate by analyzing the image data. In the image diagnosis support apparatus, the image display unit selects an attention area corresponding to at least one of the abnormal shadow candidates, and displays an enlarged display window at a position of the attention area in a displayed image. An image diagnosis support apparatus, wherein an enlarged image of the attention area is displayed in a set enlarged display window. 2. An image diagnosis support apparatus comprising: image information storage means for storing image data and finding information associated with the image data; and image display means for displaying the stored image data. Means for determining an abnormal shadow candidate based on the finding information corresponding to the image data, selecting an attention area corresponding to at least one abnormal shadow candidate from the determined abnormal shadow candidates, An enlarged display window is set at the position of the noted area, and an enlarged image of the noted area is displayed in the set enlarged display window. 3. The image / diagnosis support apparatus according to claim 1, wherein a ranking is given to the abnormal shadow candidates, and the attention area is sequentially switched according to the given ranking. 4. The apparatus according to claim 3, wherein the order is determined based on the certainty factor of the abnormal shadow candidate or the type of abnormality. 5. The image / diagnosis support apparatus according to claim 3, wherein the attention area is sequentially switched in accordance with a signal input from the switching signal input means. 6. The image diagnosis support apparatus according to claim 3, wherein the attention area is sequentially switched at predetermined time intervals. 7. The image diagnosis support apparatus according to claim 1, wherein different image processing is performed on a region inside and outside of the enlarged display window. 8. The apparatus according to claim 7, wherein the image processing is gradation processing, frequency processing, dynamic range compression processing, or interpolation processing. 9. The image diagnosis support apparatus according to claim 7, wherein an image processing condition is determined based on an enlargement ratio of the image, and image processing is performed based on the determined image processing condition. 10. The image diagnosis support apparatus according to claim 7, wherein image processing conditions are determined based on the type of abnormality, and image processing is performed based on the determined image processing conditions. 11. The apparatus according to claim 1, wherein a size of the enlarged display window is determined based on a size of the abnormal shadow candidate. 12. The image diagnosis support apparatus according to claim 1, wherein the magnification of the image is determined based on the pixel size of the image and the resolution of the image display means. 13. The apparatus according to claim 12, wherein the enlargement ratio is determined so as to be an integral multiple of the enlargement ratio when the subject in the image is displayed at the actual size. . 14. An image diagnosis support apparatus according to claim 1, wherein information on an enlargement ratio of the image is displayed together with the image. 15. An enlargement ratio is converted into a magnification value based on the enlargement ratio when a subject in an image is displayed in a full size using the pixel size of the image and the resolution of the image display means. The image diagnosis support apparatus according to claim 14, wherein: 16. An enlarged display control signal for changing one of a position of an enlarged display window, a size of the enlarged display window, an enlargement ratio of an image in the enlarged display window, and an image processing condition of an image in the enlarged display window. The image diagnosis support apparatus according to claim 1 or 2, further comprising an input unit. 17. The apparatus according to claim 1, wherein a mark is added near an abnormal shadow candidate position in the displayed image and displayed.